© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 7998
    Prev
    Next
    INDEX
    Explanations

    technical terms related to engineering and design for safety mechanisms and functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Action intended "to" accomplish something

    np_acts-logits-general · gemini-2.0-flash

    prevent, absorb, protect, direct

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     GenerationType
    -0.64
    Rhestr
    -0.58
    zugehen
    -0.51
    AndEndTag
    -0.50
    SPATH
    -0.50
    orylation
    -0.48
     apost
    -0.48
     jdbcTemplate
    -0.48
     éto
    -0.48
    gelöst
    -0.47
    POSITIVE LOGITS
     prevent
    0.81
     traps
    0.80
     absorb
    0.79
     trap
    0.79
    OGND
    0.77
     absorbs
    0.75
    trap
    0.72
     minim
    0.72
     trapping
    0.71
     prevents
    0.70
    Activations Density 0.424%

    No Known Activations